{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:363GGNWGHWLQQVYNQSKZJSRT3O","short_pith_number":"pith:363GGNWG","schema_version":"1.0","canonical_sha256":"dfb66336c63d9708570d849594ca33dbb6630dcc3744a64db3060c63b3532645","source":{"kind":"arxiv","id":"1906.08650","version":2},"attestation_state":"computed","paper":{"title":"3D Instance Segmentation via Multi-Task Metric Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bernard Ghanem, Jean Lahoud, Marc Pollefeys, Martin R. Oswald","submitted_at":"2019-06-20T14:14:16Z","abstract_excerpt":"We propose a novel method for instance label segmentation of dense 3D voxel grids. We target volumetric scene representations, which have been acquired with depth sensors or multi-view stereo methods and which have been processed with semantic 3D reconstruction or scene completion methods. The main task is to learn shape information about individual object instances in order to accurately separate them, including connected and incompletely scanned objects. We solve the 3D instance-labeling problem with a multi-task learning strategy. The first goal is to learn an abstract feature embedding, wh"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1906.08650","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-20T14:14:16Z","cross_cats_sorted":[],"title_canon_sha256":"508bffab340138833aaade550f3656481adfbcc1bef367f69e08f8ffd0ca1ef3","abstract_canon_sha256":"4eee3c3a0b6c2d387e8ac5496d477a94682c7eda2fa4b44f9d29a0ada231a704"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:16:20.531715Z","signature_b64":"tYB5vSH1omgwYE7hwEOAsowgcLMJem33S5ArtTSyOf6CqwR5wptc37TJLUzXI4vtSppkCdOAuc03gd84pomTDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfb66336c63d9708570d849594ca33dbb6630dcc3744a64db3060c63b3532645","last_reissued_at":"2026-07-05T00:16:20.531248Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:16:20.531248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"3D Instance Segmentation via Multi-Task Metric Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bernard Ghanem, Jean Lahoud, Marc Pollefeys, Martin R. Oswald","submitted_at":"2019-06-20T14:14:16Z","abstract_excerpt":"We propose a novel method for instance label segmentation of dense 3D voxel grids. We target volumetric scene representations, which have been acquired with depth sensors or multi-view stereo methods and which have been processed with semantic 3D reconstruction or scene completion methods. The main task is to learn shape information about individual object instances in order to accurately separate them, including connected and incompletely scanned objects. We solve the 3D instance-labeling problem with a multi-task learning strategy. The first goal is to learn an abstract feature embedding, wh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.08650","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1906.08650/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1906.08650","created_at":"2026-07-05T00:16:20.531298+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.08650v2","created_at":"2026-07-05T00:16:20.531298+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.08650","created_at":"2026-07-05T00:16:20.531298+00:00"},{"alias_kind":"pith_short_12","alias_value":"363GGNWGHWLQ","created_at":"2026-07-05T00:16:20.531298+00:00"},{"alias_kind":"pith_short_16","alias_value":"363GGNWGHWLQQVYN","created_at":"2026-07-05T00:16:20.531298+00:00"},{"alias_kind":"pith_short_8","alias_value":"363GGNWG","created_at":"2026-07-05T00:16:20.531298+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.08900","citing_title":"DSER: Spectral Epipolar Representation for Efficient Light Field Depth Estimation","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/363GGNWGHWLQQVYNQSKZJSRT3O","json":"https://pith.science/pith/363GGNWGHWLQQVYNQSKZJSRT3O.json","graph_json":"https://pith.science/api/pith-number/363GGNWGHWLQQVYNQSKZJSRT3O/graph.json","events_json":"https://pith.science/api/pith-number/363GGNWGHWLQQVYNQSKZJSRT3O/events.json","paper":"https://pith.science/paper/363GGNWG"},"agent_actions":{"view_html":"https://pith.science/pith/363GGNWGHWLQQVYNQSKZJSRT3O","download_json":"https://pith.science/pith/363GGNWGHWLQQVYNQSKZJSRT3O.json","view_paper":"https://pith.science/paper/363GGNWG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.08650&json=true","fetch_graph":"https://pith.science/api/pith-number/363GGNWGHWLQQVYNQSKZJSRT3O/graph.json","fetch_events":"https://pith.science/api/pith-number/363GGNWGHWLQQVYNQSKZJSRT3O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/363GGNWGHWLQQVYNQSKZJSRT3O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/363GGNWGHWLQQVYNQSKZJSRT3O/action/storage_attestation","attest_author":"https://pith.science/pith/363GGNWGHWLQQVYNQSKZJSRT3O/action/author_attestation","sign_citation":"https://pith.science/pith/363GGNWGHWLQQVYNQSKZJSRT3O/action/citation_signature","submit_replication":"https://pith.science/pith/363GGNWGHWLQQVYNQSKZJSRT3O/action/replication_record"}},"created_at":"2026-07-05T00:16:20.531298+00:00","updated_at":"2026-07-05T00:16:20.531298+00:00"}